TencentOS Server 4: nodejs20 (TSSA-2025:0293)

The version of Tencent Linux installed on the remote TencentOS Server 4 host is prior to tested version. It is, therefore, affected by multiple vulnerabilities as referenced in the TSSA-2025:0293 advisory. Package updates are available for TencentOS Server 4 that fix the following vulnerabilities...

CVE-2025-45988

Blink routers BL-WR9000 V2.4.9 , BL-AC2100AZ3 V1.0.4, BL-X10AC8 v1.0.5 , BL-LTE300 v1.2.3, BL-F1200AT1 v1.0.0, BL-X26AC8 v1.2.8, BLAC450MAE4 v4.0.0 and BL-X26DA3 v1.2.7 were discovered to contain multiple command injection vulnerabilities via the cmd parameter in the bsSetCmd function...

I Know What You Said: Unveiling Hardware Cache Side-Channels in Local Large Language Model Inference

Large Language Models LLMs that can be deployed locally have recently gained popularity for privacy-sensitive tasks, with companies such as Meta, Google, and Intel playing significant roles in their development. However, the security of local LLMs through the lens of hardware cache side-channels...

Exploit for Integer Overflow or Wraparound in Tesla Model_3_Firmware

Tesla Nasıl Hacklenir? — Etkileşimli Senaryo Uygulaması Bu pr...

Exploit for CVE-2025-52357

CVE-2025-52357 : Security Advisory: XSS in FD602GW-DX-R410 Rou...

New TokenBreak Attack Bypasses AI Moderation with Single-Character Text Changes

Cybersecurity researchers have discovered a novel attack technique called TokenBreak that can be used to bypass a large language model's LLM safety and content moderation guardrails with just a single character change. "The TokenBreak attack targets a text classification model's tokenization...

SOFT: Selective Data Obfuscation for Protecting LLM Fine-Tuning against Membership Inference Attacks

Whitepaper called SOFT: Selective Data Obfuscation For Protecting LLM Fine-Tuning Against Membership Inference Attacks...

Uncovering Reliable Indicators: Improving IoC Extraction from Threat Reports

Indicators of Compromise IoCs are critical for threat detection and response, marking malicious activity across networks and systems. Yet, the effectiveness of automated IoC extraction systems is fundamentally limited by one key issue: the lack of high-quality ground truth. Current extraction too...

MAYA: Addressing Inconsistencies in Generative Password Guessing through a Unified Benchmark

Recent advances in generative models have led to their application in password guessing, with the aim of replicating the complexity, structure, and patterns of human-created passwords. Despite their potential, inconsistencies and inadequate evaluation methodologies in prior research have hindered...

ObfusBFA: a Holistic Approach to Safeguarding DNNs from Different Types of Bit-Flip Attacks

Bit-flip attacks BFAs represent a serious threat to Deep Neural Networks DNNs, where flipping a small number of bits in the model parameters or binary code can significantly degrade the model accuracy or mislead the model prediction in a desired way. Existing defenses exclusively focus on...

CVE-2025-31052

Deserialization of Untrusted Data vulnerability in themeton The Fashion - Model Agency One Page Beauty Theme nrgfashion allows Object Injection.This issue affects The Fashion - Model Agency One Page Beauty Theme: from n/a through = 1.4.4...

How to Build a Lean Security Model: 5 Lessons from River Island

In today’s security landscape, budgets are tight, attack surfaces are sprawling, and new threats emerge daily. Maintaining a strong security posture under these circumstances without a large team or budget can be a real challenge. Yet lean security models are not only possible - they can be highl...

LLMail-Inject: a Dataset from a Realistic Adaptive Prompt Injection Challenge

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models LLMs to distinguish between instructions and data in their inputs. Despite numerous defense proposals, the systematic evaluation against adaptive adversaries remains limited, even when successful attacks ca...

DiffUMI: Training-Free Universal Model Inversion Via Unconditional Diffusion for Face Recognition

Face recognition technology presents serious privacy risks due to its reliance on sensitive and immutable biometric data. To address these concerns, such systems typically convert raw facial images into embeddings, which are traditionally viewed as privacy-preserving. However, model inversion...

LLMs Cannot Reliably Judge (Yet?): a Comprehensive Assessment on the Robustness of LLM-As-A-Judge

Large Language Models LLMs have demonstrated remarkable intelligence across various tasks, which has inspired the development and widespread adoption of LLM-as-a-Judge systems for automated model testing, such as red teaming and benchmarking. However, these systems are susceptible to adversarial...

GenBreak: Red Teaming Text-To-Image Generators Using Large Language Models

Text-to-image T2I models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation...

Empirical Quantification of Spurious Correlations in Malware Detection

End-to-end deep learning exhibits unmatched performance for detecting malware, but such an achievement is reached by exploiting spurious correlations -- features with high relevance at inference time, but known to be useless through domain knowledge. While previous work highlighted that deep...

Learning Obfuscations of LLM Embedding Sequences: Stained Glass Transform

The high cost of ownership of AI compute infrastructure and challenges of robust serving of large language models LLMs has led to a surge in managed Model-as-a-service deployments. Even when enterprises choose on-premises deployments, the compute infrastructure is typically shared across many tea...

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods

In this work, we show that some machine unlearning methods may fail when subjected to straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families, and employ output-based, logit-based, and probe analysis to determine to what extent supposedly...

Expert-In-The-Loop Systems with Cross-Domain and In-Domain Few-Shot Learning for Software Vulnerability Detection

As cyber threats become more sophisticated, rapid and accurate vulnerability detection is essential for maintaining secure systems. This study explores the use of Large Language Models LLMs in software vulnerability assessment by simulating the identification of Python code with known Common...